Geekbench AI Score

337
Single Precision Score
345
Half Precision Score
669
Quantized Score
Geekbench AI 1.1.0 for Android AArch64

Result Information

Upload Date November 21 2024 03:09 AM
Views 1

System Information

AI Information
Framework TensorFlow Lite
Backend CPU
Device ARM ARMv8
System Information
Operating System Android 15
Model UNISOC ums9230_6h10_Natv
Model IDUNISOC ums9230_6h10_Natv
Motherboard ums9230_6h10
Governoruscfreq
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.82 GHz
Cluster 18 Cores @ 1.82 GHz
Memory Information
Size 5.57 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 191
35.4 IPS
 
Image Classification (HP)
100% 187
34.9 IPS
 
Image Classification (Q)
100% 498
92.6 IPS
 
Image Segmentation (SP)
100% 227
3.69 IPS
 
Image Segmentation (HP)
100% 231
3.75 IPS
 
Image Segmentation (Q)
98% 651
10.6 IPS
 
Pose Estimation (SP)
100% 779
0.91 IPS
 
Pose Estimation (HP)
100% 781
0.91 IPS
 
Pose Estimation (Q)
84% 1343
1.59 IPS
 
Object Detection (SP)
100% 204
16.2 IPS
 
Object Detection (HP)
100% 199
15.8 IPS
 
Object Detection (Q)
83% 482
38.9 IPS
 
Face Detection (SP)
100% 446
5.30 IPS
 
Face Detection (HP)
100% 443
5.27 IPS
 
Face Detection (Q)
95% 1216
14.5 IPS
 
Depth Estimation (SP)
100% 379
2.92 IPS
 
Depth Estimation (HP)
99% 517
3.98 IPS
 
Depth Estimation (Q)
64% 1295
11.9 IPS
 
Style Transfer (SP)
89% 1559
2.02 IPS
 
Style Transfer (HP)
89% 1609
2.09 IPS
 
Style Transfer (Q)
98% 3392
4.37 IPS
 
Image Super-Resolution (SP)
100% 308
11.4 IPS
 
Image Super-Resolution (HP)
100% 288
10.7 IPS
 
Image Super-Resolution (Q)
97% 750
27.8 IPS
 
Text Classification (SP)
100% 159
212.6 IPS
 
Text Classification (HP)
100% 163
217.2 IPS
 
Text Classification (Q)
88% 199
269.0 IPS
 
Machine Translation (SP)
100% 214
3.68 IPS
 
Machine Translation (HP)
100% 210
3.61 IPS
 
Machine Translation (Q)
50% 108
3.85 IPS
 

Compare

Set Baseline Geekbench 6 now available